# OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking

arXiv: https://arxiv.org/abs/2501.09751 · HTML: https://mlsanity.com/paper/2501.09751/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 32 of its 54 references that are in the map.
- First posted on arXiv 16 Jan 2025.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)
- Retrieval-augmented generation / [RAG pipeline design and evaluation](https://mlsanity.com/rag/rag-pipeline-design-and-evaluation/)

## Builds on (most cited first, 30 of 32)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [Reading Wikipedia to Answer Open-Domain Questions](https://mlsanity.com/paper/1704.00051/) (2017)
- [In-Context Retrieval-Augmented Language Models](https://mlsanity.com/paper/2302.00083/) (2023)
- [ELI5: Long Form Question Answering](https://mlsanity.com/paper/1907.09190/) (2019)
- [Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models](https://mlsanity.com/paper/2405.01535/) (2024)
- [Generating Wikipedia by Summarizing Long Sequences](https://mlsanity.com/paper/1801.10198/) (2018)
- [WebWalker: Benchmarking LLMs in Web Traversal](https://mlsanity.com/paper/2501.07572/) (2025)
- [Long-form factuality in large language models](https://mlsanity.com/paper/2403.18802/) (2024)
- [Language agents achieve superhuman synthesis of scientific knowledge](https://mlsanity.com/paper/2409.13740/) (2024)
- [RecurrentGPT: Interactive Generation of (Arbitrarily) Long Text](https://mlsanity.com/paper/2305.13304/) (2023)
- [Read before Generate! Faithful Long Form Question Answering with Machine Reading](https://mlsanity.com/paper/2203.00343/) (2022)
- [HelloBench: Evaluating Long Text Generation Capabilities of Large Language Models](https://mlsanity.com/paper/2409.16191/) (2024)
- [Into the Unknown Unknowns: Engaged Human Learning through Participation in Language Model Agent Conversations](https://mlsanity.com/paper/2408.15232/) (2024)
- [A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoning](https://mlsanity.com/paper/2501.02497/) (2025)
- [Leveraging Large Language Models for NLG Evaluation: Advances and Challenges](https://mlsanity.com/paper/2401.07103/) (2024)
- [Suri: Multi-constraint Instruction Following for Long-form Text Generation](https://mlsanity.com/paper/2406.19371/) (2024)
- [LongGenBench: Long-context Generation Benchmark](https://mlsanity.com/paper/2410.04199/) (2024)
- [Weaver: Foundation Models for Creative Writing](https://mlsanity.com/paper/2401.17268/) (2024)
- [PROXYQA: An Alternative Framework for Evaluating Long-Form Text Generation with Large Language Models](https://mlsanity.com/paper/2401.15042/) (2024)
- [Language Models can Self-Lengthen to Generate Long Texts](https://mlsanity.com/paper/2410.23933/) (2024)
- [Beyond Summarization: Designing AI Support for Real-World Expository Writing Tasks](https://mlsanity.com/paper/2304.02623/) (2023)
- [AutoPatent: A Multi-Agent Framework for Automatic Patent Generation](https://mlsanity.com/paper/2412.09796/) (2024)
- [DOC: Improving Long Story Coherence With Detailed Outline Control](https://mlsanity.com/paper/2212.10077/) (2022)
- [Expository Text Generation: Imitate, Retrieve, Paraphrase](https://mlsanity.com/paper/2305.03276/) (2023)
- [Open-Domain Question-Answering for COVID-19 and Other Emergent Domains](https://mlsanity.com/paper/2110.06962/) (2021)

## Built on by (most cited first, 18 of 18)

- [WebThinker: Empowering Large Reasoning Models with Deep Research Capability](https://mlsanity.com/paper/2504.21776/) (2025)
- [WebDancer: Towards Autonomous Information Seeking Agency](https://mlsanity.com/paper/2505.22648/) (2025)
- [Synergizing RAG and Reasoning: A Systematic Review](https://mlsanity.com/paper/2504.15909/) (2025)
- [O2-Searcher: A Searching-based Agent Model for Open-Domain Open-Ended Question Answering](https://mlsanity.com/paper/2505.16582/) (2025)
- [SynWorld: Virtual Scenario Synthesis for Agentic Action Knowledge Refinement](https://mlsanity.com/paper/2504.03561/) (2025)
- [LongDPO: Unlock Better Long-form Generation Abilities for LLMs via Critique-augmented Stepwise Information](https://mlsanity.com/paper/2502.02095/) (2025)
- [DataSTORM: Deep Research on Large-Scale Databases using Exploratory Data Analysis and Data Storytelling](https://mlsanity.com/paper/2604.06474/) (2026)
- [WikiAutoGen: Towards Multi-Modal Wikipedia-Style Article Generation](https://mlsanity.com/paper/2503.19065/) (2025)
- [Deep-Research Agents Can Be Poisoned via User-Generated Content](https://mlsanity.com/paper/2605.24245/) (2026)
- [HetaRAG: Hybrid Deep Retrieval-Augmented Generation across Heterogeneous Data Stores](https://mlsanity.com/paper/2509.21336/) (2025)
- [LLM×MapReduce-V2: Entropy-Driven Convolutional Test-Time Scaling for Generating Long-Form Articles from Extremely Long Resources](https://mlsanity.com/paper/2504.05732/) (2025)
- [LogiStory: A Logic-Aware Framework for Multi-Image Story Visualization](https://mlsanity.com/paper/2603.28082/) (2026)
- [DeepWriter: A Fact-Grounded Multimodal Writing Assistant Based On Offline Knowledge Base](https://mlsanity.com/paper/2507.14189/) (2025)
- [AgentCPM-Report: Interleaving Drafting and Deepening for Open-Ended Deep Research](https://mlsanity.com/paper/2602.06540/) (2026)
- [ConvergeWriter: Data-Driven Bottom-Up Article Construction](https://mlsanity.com/paper/2509.12811/) (2025)
- [AI4Reading: Chinese Audiobook Interpretation System Based on Multi-Agent Collaboration](https://mlsanity.com/paper/2512.23300/) (2025)
- [VeriTrace: Evolving Mental Models for Deep Research Agents](https://mlsanity.com/paper/2605.26081/) (2026)
- [LongCat-DeepResearch Technical Report](https://mlsanity.com/paper/2609.36071/) (2026)

## Abstract (arXiv)

Machine writing with large language models often relies on retrieval-augmented generation. However, these approaches remain confined within the boundaries of the model's predefined scope, limiting the generation of content with rich information. Specifically, vanilla-retrieved information tends to lack depth, novelty, and suffers from redundancy, which negatively impacts the quality of generated articles, leading to shallow, unoriginal, and repetitive outputs. To address these issues, we propose OmniThink, a slow-thinking machine writing framework that emulates the human-like process of iterative expansion and reflection. The core idea behind OmniThink is to simulate the cognitive behavior of learners as they slowly deepen their knowledge of the topics. Experimental results demonstrate that OmniThink improves the knowledge density of generated articles without compromising metrics such as coherence and depth. Human evaluations and expert feedback further highlight the potential of OmniThink to address real-world challenges in the generation of long-form articles. Code is available at https://github.com/zjunlp/OmniThink.